Compare approval support by demographic group.
Inspect overall accuracy and unequal outcomes.
Choose two evaluations.
Compare approval, false rejection, false acceptance, and review rates by group, then revisit thresholds, data, operations, and remedy with people.
Detailed explanation
Outcome and error differences are visible.
Outcome and error differences are visible.
Measurement leads to operational improvement and recourse.
Measurement leads to operational improvement and recourse.
Accuracy and harm distribution can differ.
Accuracy and harm distribution can differ.
Proxy variables and outcome gaps can remain.
Proxy variables and outcome gaps can remain.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 4.1の公平性指標、影響、救済を確認する。Expected result
グループ別の結果差を測定し、閾値や業務運用の見直しへつなげられる。Key points
- Approval rate
- False rejection
- Remedy
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.